INDEX

Explanations

times, numbers, and events

The neuron fires on numerical schedule details—times, dates, and other numerals indicating when events occur.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 then

-1.34

 already

-1.34

 entonces

-1.32

ものの

-1.22

}}+\

-1.18

🇵

-1.18

 Preferencias

-1.16

 that

-1.14

kaç

-1.13

 rosario

-1.12

POSITIVE LOGITS

喏

1.38

 fenó

1.34

дневно

1.30

も含

1.29

ᡴ

1.27

 brilh

1.20

 humeur

1.18

 スリーブ

1.18

 sustent

1.16

 estran

1.16

Activations Density 0.001%